Information-theoretic bounds and phase transitions in clustering, sparse PCA, and submatrix localization

Abstract

We study the problem of detecting a structured, low-rank signal matrix corrupted with additive Gaussian noise. This includes clustering in a Gaussian mixture model, sparse PCA, and submatrix localization. Each of these problems is conjectured to exhibit a sharp information-theoretic threshold, below which the signal is too weak for any algorithm to detect. We derive upper and lower bounds on these thresholds by applying the first and second moment methods to the likelihood ratio between these "planted models" and null models where the signal matrix is zero. Our bounds differ by at most a factor of root two when the rank is large (in the clustering and submatrix localization problems, when the number of clusters or blocks is large) or the signal matrix is very sparse. Moreover, our upper bounds show that for each of these problems there is a significant regime where reliable detection is information- theoretically possible but where known algorithms such as PCA fail completely, since the spectrum of the observed matrix is uninformative. This regime is analogous to the conjectured 'hard but detectable' regime for community detection in sparse graphs.

For sparse PCA and submatrix localization, we determine the information-theoretic threshold exactly in the limit where the number of blocks is large or the signal matrix is very sparse based on a conditional second moment method, closing the factor of root two gap in the first version

References in corpus (10)

• Asymptotic analysis of the stochastic block model for modular networks and its algorithmic applications
• Spectral redemption: clustering sparse networks
• Phase transition in the detection of modules in sparse networks
• Optimal detection of sparse principal components in high dimension
• Statistical-Computational Tradeoffs in Planted Problems and Submatrix Localization with a Growing Number of Clusters and Submatrices
• Detection of a sparse submatrix of a high-dimensional noisy matrix
• MMSE of probabilistic low-rank matrix estimation: Universality with respect to the output channel
• Optimality and Sub-optimality of PCA for Spiked Random Matrices and Synchronization
• Sparse PCA via Covariance Thresholding
• Information-theoretic thresholds for community detection in sparse networks

Cited by in corpus (5)

• Optimality and Sub-optimality of PCA I: Spiked Random Matrix Models
• Optimality and Sub-optimality of PCA for Spiked Random Matrices and Synchronization
• Two-Sample Tests for Large Random Graphs Using Network Statistics
• Robust Sparse Estimation Tasks in High Dimensions
• An Information-Percolation Bound for Spin Synchronization on General Graphs